Visualization of the detector shapes used in the "frontalface_alt2" cascade file for OpenCV.
Each cascade can have 20 or so stages. The beginning stages are easier to pass, as noted by the larger shapes. As the algorithm progresses through each stage, some image subregions are quickly rejected. This allows the algorithm to quickly scan the image and not waste on unimportant areas. While towards the end of the visualization, the shapes will become smaller, more complicated and more picky.
The Viola Jones algorithm compares the difference between the dark and light areas defined by the shapes and measures whether this difference falls within a threshold.
Rendered at 12fps
Part of my research for cvdazzle.com
Loading more stuff…
Hmm…it looks like things are taking a while to load. Try again?